hmem
Active·★ 24·MIT·Updated 2026-07-21
hmem is a memory system for AI agents that persists project context across sessions, devices, and AI providers. It uses a 5-level lazy loading architecture to minimize token usage while retaining full details. It supports auto-logging, background checkpoints, and cross-platform sync.
#ai-agents#ai-tools#claude#llm#mcp#mcp-server#mcp-servers#memory
01
Features
015-level lazy loading to minimize token usage
02Automatic session logging and background checkpoints via Haiku
03Cross-provider and cross-tool support
04Project-based memory organization
05Encrypted sync across devices
02
Compatibility
Claude Code
Native
Verified via docs
Claude
Native
Verified via docs
Gemini CLI
Supported
Verified via docs
GPT
Supported
Verified via docs
DeepSeek
Supported
Verified via docs
Cursor
Supported
Verified via docs
03
Quick start
1
$ npm install -g hmem-mcp
2
$ npx hmem init
04
Use cases
↳AI coding assistants that need to maintain project context across sessions
↳Multi-device workflow where different agents continue the same project
↳Knowledge management for personal AI assistants
05
Alternatives
its-over-9k★ 0
Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.
YourMemory★ 270
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
multi-agent-memory★ 64
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
tradememory-protocol★ 1.4k
Memory layer for AI trading agents. Outcome-weighted recall, autonomous strategy evolution, 15 MCP tools.
open-ontologies★ 1.2k
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.
AgentRecall-MCP★ 371
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
Comments
Log in to leave a comment
No comments yet. Be the first!